What one founder's past says about AI's future

Summary

TED Radio Hour: What One Founder’s Past Says About AI’s Future

Host: Minouche Zomorodi
Guest: Mustafa Suleiman, CEO of Microsoft AI and Co-Founder of DeepMind
Release Date: December 20, 2024

---

Introduction

In this compelling episode of TED Radio Hour, host Minouche Zomorodi engages with Mustafa Suleiman, a pivotal figure in the field of artificial intelligence (AI). Suleiman, the CEO of Microsoft AI and co-founder of DeepMind, shares his journey from establishing one of the first AI-focused companies to shaping the future of AI at Microsoft. The discussion delves into the transformative potential of AI, its ethical implications, and the strategies necessary to harness its benefits while mitigating risks.

---

Early Beginnings and Founding DeepMind

[00:56] Mustafa Suleiman reflects on his initial foray into creating supportive infrastructures for marginalized communities. In 2002, as a student at Oxford University, Suleiman co-founded the Muslim Youth Helpline with a friend. This helpline provided much-needed counseling services to young British Muslims facing challenges such as Islamophobia, bullying, and self-harm.

“Young British Muslims were feeling judged by 9/11 as though they were responsible or somehow complicit. There was a lot of Islamophobia... people were just looking to find support in a language that made sense to them.”
— Mustafa Suleiman, [02:14]

---

Building DeepMind and Achieving Breakthroughs

By 2010, Suleiman, alongside his co-founder Demis Hassabis, established DeepMind, one of the earliest companies dedicated to developing artificial general intelligence (AGI). Their mission was twofold: to solve intelligence and to use it to make the world a better place.

[07:18] Suleiman emphasizes the ambitious nature of DeepMind's endeavors during a time when AGI was largely dismissed as science fiction.

“We were misfits and kind of outsiders... It was very clear... the consequences for humanity were going to be significant.”
— Mustafa Suleiman, [08:26]

DeepMind’s acquisition by Google in 2014 marked a significant milestone, granting the team unprecedented resources to pursue groundbreaking research. Among their notable achievements was AlphaFold, an AI system capable of predicting protein structures with remarkable accuracy, a feat that revolutionized computational biology.

“AlphaFold was just one of the ways that computers were solving biological problems.”
— Minouche Zomorodi, [18:42]

---

Transition to Microsoft AI and the Creation of Copilot

In 2022, frustrated by the slow pace of innovation at Google, Suleiman departed DeepMind to establish his own AI venture. His goal was to develop Copilot, an AI companion designed to assist users in various aspects of daily life by being available around the clock.

[22:06] Discussing the inception of Copilot, Suleiman shares:

“The product that we're building at Microsoft is called Copilot. It's an aide, it's an assistant, it's in your corner, aligned to your interests, on your team, backing you up.”
— Mustafa Suleiman, [22:06]

Copilot aims to be more than just a tool; it aspires to become a personal confidant that can help with tasks ranging from managing schedules to providing emotional support without judgment.

---

Envisioning the Future of AI

Suleiman paints a vivid picture of a future where AI is seamlessly integrated into every facet of human life. He envisions AI companions becoming as ubiquitous as smartphones, revolutionizing how we interact with technology.

[26:50] On the transformative impact of AI, Suleiman states:

“These will be infinitely knowledgeable... they'll have exceptional EQ... They will be companions, confidants, colleagues, friends, and partners.”
— Mustafa Suleiman, [32:49]

He underscores the rapid advancements in AI capabilities, highlighting how large language models have evolved to handle complex tasks with unprecedented proficiency.

---

Ethical Considerations and AI Safety

A significant portion of the discussion centers on the ethical challenges posed by AI. Suleiman outlines four critical attributes that could make AI both powerful and potentially hazardous:

1. Asymmetry – Concentration of vast data and capabilities in the hands of few individuals or entities.

   “We're concentrating knowledge... individual actors or smaller groups... can have a massive one to many broadcast effect.”
   — Mustafa Suleiman, [38:53]

2. Hyperevolution – The rapid and autonomous evolution of AI software, outpacing human oversight.

   “Software itself just evolving in hyper real time.”
   — Mustafa Suleiman, [39:45]

3. Omni Use – The ability of AI to perform a wide array of tasks across various domains, increasing its influence.

   “Your AI companion will make phone calls, call other AIs, or call other humans...”
   — Mustafa Suleiman, [40:38]

4. Autonomy – AI systems making decisions and taking actions without human intervention.

   “Autonomous weapon systems operate on battlefields... without direct human oversight.”
   — Copilot, [41:28]

Suleiman advocates for robust oversight and ethical guidelines to ensure AI technologies are developed and deployed responsibly. He emphasizes the need to view AI not just as tools but as emerging digital entities that require careful regulation.

“AIs are clearly more dynamic, more ambiguous, more integrated and more emergent than mere tools...”
— Mustafa Suleiman, [42:37]

---

Strategies for Mitigating AI Risks

Addressing the potential dangers of AI, Suleiman outlines strategies to contain and guide its development:

1. Enhanced Research on AI Safety – Increasing the number of researchers dedicated to AI safety to anticipate and mitigate risks.

   “We have a big safety team... ensuring the AI isn't too sycophantic... pushing back on views constructively.”
   — Mustafa Suleiman, [45:13]

2. Regulation and Oversight – Implementing mandatory testing and regulatory frameworks to oversee AI development before market release.

   “I think sometime before 2030 we will need something like that.”
   — Mustafa Suleiman, [48:45]

3. Ethical Design Principles – Incorporating empathy, kindness, and emotional intelligence into AI systems to foster positive interactions.

   “It's about being respectful and acknowledging that people do genuinely feel aggrieved...”
   — Mustafa Suleiman, [45:13]

4. Public Engagement and Transparency – Encouraging open dialogue about AI’s capabilities and limitations to build trust and informed public discourse.

---

Balancing Innovation with Responsibility

Suleiman acknowledges the delicate balance between advancing AI technologies and ensuring they are aligned with societal good. He underscores the importance of maintaining privacy and security while delivering high-utility AI products.

“The utility will drive the way... we have to make sure that we have the strongest privacy and security infrastructure...”
— Mustafa Suleiman, [50:20]

He also likens AI to nuclear fusion—a transformative force that requires careful stewardship to harness its benefits while preventing misuse.

“AI is to the mind what nuclear fusion is to energy. Limitless, abundant, world-changing.”
— Mustafa Suleiman, [51:55]

---

Concluding Thoughts: AI as a Reflection of Humanity

In his closing remarks, Suleiman presents AI as an extension of human ingenuity and empathy. He emphasizes that AI embodies the collective achievements and values of humanity, suggesting that its future lies in reflecting our best traits.

“AI is us. It's all of us. And this is perhaps the most promising and vital thing of all.”
— Mustafa Suleiman, [53:30]

Suleiman calls for intentional and ethical AI development, highlighting it as the greatest challenge and opportunity of the 21st century.

---

Final Reflections

Mustafa Suleiman's insights offer a profound exploration of AI's trajectory, urging both innovation and caution. His vision encapsulates the immense potential of AI to enhance human life while advocating for the necessary frameworks to safeguard against its inherent risks. This episode serves as a crucial guide for understanding the delicate interplay between technological advancement and ethical responsibility in shaping the future of AI.

---

Notable Quotes:

• Mustafa Suleiman [02:14]:
  "Young British Muslims were feeling judged by 9/11 as though they were responsible or somehow complicit. There was a lot of Islamophobia... people were just looking to find support in a language that made sense to them."

• Mustafa Suleiman [08:26]:
  "We were misfits and kind of outsiders... It was very clear... the consequences for humanity were going to be significant."

• Mustafa Suleiman [22:06]:
  "The product that we're building at Microsoft is called Copilot. It's an aide, it's an assistant, it's in your corner, aligned to your interests, on your team, backing you up."

• Mustafa Suleiman [38:53]:
  "We're concentrating knowledge... individual actors or smaller groups... can have a massive one to many broadcast effect."

• Mustafa Suleiman [42:37]:
  "AIs are clearly more dynamic, more ambiguous, more integrated and more emergent than mere tools..."

• Mustafa Suleiman [51:55]:
  "AI is to the mind what nuclear fusion is to energy. Limitless, abundant, world-changing."

---

This detailed summary encapsulates the essence of Mustafa Suleiman’s vision for AI, highlighting both its transformative potential and the ethical considerations necessary to navigate its future responsibly. Through thoughtful dialogue, the episode underscores the imperative to balance innovation with safeguards, ensuring that AI serves as a positive force for humanity.

Transcript

[Minouche Zamarodi]

This message comes from Discover. This time of year, people feel reinvigorated for another mood booster. Discover will automatically double all the cash back you've earned on your credit card at the end of your first year. See [e-mail] credit card. This is the TED Radio Hour. Each week, groundbreaking TED Talks.

[Mustafa Suleiman]

Our job now is to dream big.

[Minouche Zamarodi]

Delivered at TED Conferences to bring about.

[Mustafa Suleiman]

The future we want to see around the world.

[Minouche Zamarodi]

To understand who we are from the we bring you speakers and ideas that will surprise you. You just don't know what you're gonna find challenge you.

[Unknown]

We truly have to ask ourselves, like.

[Minouche Zamarodi]

Why is it noteworthy and even change you? I literally feel like I'm a different person. Yes. Do you feel that way? Ideas worth spreading From TED and NPR. I'm Minouche Zamorodi.

[Mustafa Suleiman]

It was about a year after 9 11.

[Minouche Zamarodi]

This is Mustafa Suleiman. In 2002, Mustafa was a student at Oxford University when a friend decided to start a helpline for young British Muslims.

[Mustafa Suleiman]

A good friend of mine at the time had just started the first prototype. One evening session, I think it was a Thursday evening, of offering counseling services on the phone.

[Minouche Zamarodi]

Mustafa was intrigued. He ended up joining the project to help grow it.

[Mustafa Suleiman]

And we became essentially co founders.

[Minouche Zamarodi]

Quickly. Their service was in hot demand.

[Mustafa Suleiman]

You know, it was a pretty remarkable time because, you know, young British Muslims were feeling judged by 911 as though they were responsible or somehow complicit. There was a lot of Islamophobia, but.

[Minouche Zamarodi]

What they found these young people needed was really just someone to talk to.

[Mustafa Suleiman]

Most of the challenges that they were working through were, you know, the sort of conventional things that, you know, a young person might deal with, like relationships, bullying, self harm, increasing homophobia in the community. And fundamentally, I think people were just looking to find support in a language that made sense to them, you know, like a London accent using sort of Islamic terminology and having a broader understanding of the, you know, whether it was a Bangladeshi or Pakistani culture or an Arab culture combined with the religious foundation and just being able to reflect back, that empathy went a long way.

[Minouche Zamarodi]

Twenty years later, the Muslim Youth Helpline is still going strong. And Mustafa Suleiman now lives in Silicon Valley where he's been working on another kind of helper.

[Mustafa Suleiman]

I am the CEO of Microsoft AI and I work on building new AI systems and products. These days, I'm working on an AI.

[Minouche Zamarodi]

Companion with artificial intelligence and the backing of one of the biggest tech companies in the world. Mustafa Suleiman wants us each to have our own digital assistant.

[Unknown]

I Can get philosophical, creative, or poetic if you like.

[Minouche Zamarodi]

Available 24 7. Kind of like a personal helpline.

[Copilot]

I can be your sounding board at as you work through challenges, I can.

[Mustafa Suleiman]

Write stories, brainstorm ideas.

[Unknown]

Think of me as your superpower in your pocket.

[Mustafa Suleiman]

How can it serve you? You know, how can it support you? How can it save you time? How can it reduce your anxiety? How can it help make you feel smarter and more confident and more prepared to go about your day with no judgment, no pressure?

[Copilot]

Hey, Manouche, nice to hear from you. What's on your mind today?

[Minouche Zamarodi]

Microsoft calls this assistant copilot, and it was released at the end of 2023. I've been playing around with it. Well, I need to interview Mustafa Suleiman, your creator. What do you think I should ask him?

[Copilot]

I go for topics like his vision for AI's role in society, the balance between innovation and ethics, and what he sees as the most exciting future possibilities for AI.

[Minouche Zamarodi]

Okay, these are good. Now can you please write the intro for this episode?

[Copilot]

Sure thing. Here's a possible intro. Hey, it's Minouche Samarodi. And today's TED Radio Hour is dedicated to a deep dive with none other than Mustafa Suleiman. Co founder of DeepMind and author of the Coming Wave, Mustafa has been a pivotal force in AI, driving both groundbreaking advancements and sparking intense debates. In this episode, we'll discuss the promises and perils of artificial intelligence and whether we're truly prepared for the wave of change it's bringing. Is AI evolving too fast for society to adapt? Are we doing enough to mitigate the risks? It's an hour of insight, reflection, and some tough questions. So let's jump in.

[Minouche Zamarodi]

Okay, that was pretty good. As co pilot noted, Mustafa Suleiman is a longtime pioneer in the field of AI. After he dropped out of Oxford University, he worked for London's mayor. He was even part of an NGOs delegation to the Copenhagen climate negotiations in 2009. He wasn't impressed.

[Mustafa Suleiman]

There were so many sort of difficult egos and entrenched sort of interests, and I just felt a sense of sort of frustration, and I felt kind of demoralized after that experience.

[Minouche Zamarodi]

Mustafa wanted to change the world. Governments and nonprofits didn't seem terribly effective, but there was one company that was managing to change the behavior of millions of people.

[Mustafa Suleiman]

Facebook was exploding at that time. It had got to 100 million monthly active users in the course of a couple of years. And it was pretty clear to me that that was gonna have a profound impact. More so than Anything I could do in, you know, sort of the world of social activism.

[Minouche Zamarodi]

Around then, Mustafa started hanging out with the older brother of a friend, a software genius named Demis Hassabis, who had been designing computer games since he was a teen. Demis saw how to make mustaf vision possible.

[Mustafa Suleiman]

And he was coming at the world from a completely different perspective, which I found really interesting. His belief was that we would just simulate, you know, complexity in the world. This new suite of methods in AI self learning systems were coming up strong and looking likely to work. And you know, we really just clicked on that kind of technical and socio cultural view of sort of how to positively impact the world.

[Minouche Zamarodi]

Together, the two decided to start one of the first AI companies ever. They called it DeepMind.

[Mustafa Suleiman]

It was very clear from that, even those early stages that if we got the technology right and it was going to be this decade that, you know, led to major, major breakthroughs, then the consequences for humanity were going to be significant.

I've been lucky enough to be working on AI for almost 15 years now.

[Minouche Zamarodi]

Mustafa Suleiman picks up the story from the TED stage.

[Mustafa Suleiman]

Back when I started to describe it as fringe would be an understatement. Researchers would say, no, no, we're only working on machine learning because working on AI was seen as way too out there. In 2010, just the very mention of the phrase AGI, artificial general intelligence would get you some seriously strange looks and even a cold shoulder you're actually building. AGI people would say, isn't that something out of science fiction? People thought it was 50 years away or 100 years away, if it was even possible at all. Talk of AI was, I guess, kind of embarrassing. People generally thought we were weird and I guess in some ways we kind of were.

The ironic thing is that many people still don't think it's possible. Many people still think that we're crazy. And at the time people really thought we were crazy. I mean, it was so far out there, like it was really strange. And we were a strange group of people. I mean, you know, Demis, our third co founder, Shane, who, you know, basically a mathematician, spent his entire career thinking about how to formalize a definition of intelligence that we could use to measure our progress in the company. We were misfits and kind of outsiders and there weren't very many people willing to back us.

[Minouche Zamarodi]

So naming the company DeepMind, what was it that you pictured in your mind that you hope to achieve?

[Mustafa Suleiman]

Yeah, I mean, we wrote our business plan in the summer of 2010 and took it to Silicon Valley to shop it around a bunch of people. And the strap line for the business plan was building artificial general intelligence safely and ethically. And then that evolved into a two line mission which was solve intelligence and use it to make the world a better place. And that dual frame was kind of the foundation of the company that our belief that science and technology was the engine of progress. And there are some downsides, but I certainly think this is the engine of creating civilization in a more healthy and sustainable way for the very long term. And if you think about it, everything that is of value in our world today is a product of us humans being able to take materials from our environment and recompose those into products and services and other compounds that are useful to us, from our lights to our carpets, to everything that you see in front of you today.

[Minouche Zamarodi]

In 2014, DeepMind ended up being acquired by Google. That must have been huge for you in terms of money, resources. You were off to the races.

[Mustafa Suleiman]

Yeah, it was a huge event. I mean, it was the largest acquisition Google's ever made outside of the us we became Google's primary AGI bet and we were empowered with tremendous resources, both people and computation to go and both do the hard science, but also work on really important applied, practical product problems. And that's where I kind of really honed my craft, if you like, as a product maker. It was just the most amazing experience. And as early as 2015, I actually ran a hackathon project in my applied group at DeepMind. And the theme of our hackathon was to find high impact ways of using our technologies for good. And so there were lots of application, there were lots of prototype hackathon experiments in healthcare there or in energy systems, both of which went on to become significant parts of DeepMind applied. And my group published three papers in Nature showing human level performance on, for example, classifying eye diseases. The top 50 eye diseases from OCT scans, three dimensional eye scans, showing that we could perform as well as a panel of radiologists in identifying cancerous tissues in mammograms, showing that we could predict the onset of sepsis and acute kidney injury, as well as the top, you know, renal doctors using vast amounts of data. And this was way back in sort of 2016, 2017, 2018, and really helped to kind of lay a foundation for the application of large scale machine learning to tough social problems. And that was very much my motivation.

[Minouche Zamarodi]

In a minute, more of the incredible breakthroughs that Mustafa and DeepMind had at Google that changed the way medicine works today and why Mustafa ended up leaving the company.

[Mustafa Suleiman]

The company was just frankly being too slow to get things into production.

[Minouche Zamarodi]

Today on the show, the CEO of Microsoft AI, Mustafa Suleiman and the future of Artificial Intelligence. I'm Anoush Zumarodi and you're listening to the TED Radio Hour from npr. Stay with us.

[Unknown]

This message comes from Capella University Learning doesn't have to get in the way of life With Capella's game changing flexpath learning format, you can set your own deadlines and learn on your own schedule. That means you don't have to put your life on hold to earn your degree. Instead, enjoy learning your way and pursue your educational and career goals without missing a beat. A different future is closer than you think with Capella University. Learn more at Capella. Eduardo this message comes from Capital One offering commercial solutions you can bank on. Now more than ever, your business faces unique challenges and opportunities. That's why Capital One offers a comprehensive suite of financial services all tailored to your short and long term goals. Backed by the strength and stability of a top 10 commercial bank, their dedicated experts work with you to build lasting success. Explore the [e-mail] Commercial A member FDIC.

This message comes from BetterHelp this holiday season, do something for a special person in your life. You give yourself the gift of better mental health. BetterHelp online therapy connects you with a qualified therapist via phone, video or live chat. It's convenient and affordable and can be done from the comfort of your own home. Having someone to talk to is truly a gift, especially during the holidays. Visit betterhelp.com NPR to get 10% off your first month support for NPR and the following message come from Mint Mobile. If saving more and spending less is one of your top goals for 2025, switch to mint Mobile. Maximize your savings with plans starting at $15 a month. When you purchase a three month plan, go to mintmobile.com radiohour $45 upfront payment required. New customers on first three month plan only. Speed slower above 40 GB on unlimited plan. Additional taxes, fees and restrictions apply. See Mint Mobile for details.

[Minouche Zamarodi]

Hey, it's Minouche. This past year we have brought you stories about AI relationships, climate change, neurotechnology, dinosaurs, privacy, human behavior, and even one about what it means to create thriving public spaces.

[Mustafa Suleiman]

All of these public spaces that we take for granted, you know, all of this social infrastructure.

[Minouche Zamarodi]

We work really hard to bring you all of these stories because that is our public service. Kind of like a park or a public library. And libraries are these beautiful hubs that.

[Mustafa Suleiman]

Can take on the shape of whatever community that uses them really needs.

[Minouche Zamarodi]

Public media is infrastructure that we all can use. It's free and it's for everyone. And our mission is to help create a more informed public. So this time of year, I want to thank you for listening and to say that one of the best ways you can support this public service is by signing up for NPR. Plus with one subscription, you are supporting all the work that NPR does and you get sponsor free episodes and perks across NPR's catalog of 25 podcasts. It's a great time to join because Throughout December and January + listeners have access to even more insights from TED speakers to help you kick off 2025 right from making big life decisions to being more hopeful to carving out time, what is important to you, we have got you covered. Just visit plus.NPR.org you can also find the link in our episode notes. And the other way you can give is to make a [e-mail] your gifts are tax deductible either way. Thank you so much for being here. And now let's get back to the show. It's the TED Radio Hour from npr. I'm Minouche Zamarodi. Today on the show, we're spending the hour with Mujah Mustafa Suleiman, the CEO of Microsoft AI, who was the co founder of one of the first AI tech companies ever, DeepMind. The company was acquired by Google in 2014 and Mustafa and his co founder Demis Hassabis, went on to have numerous scientific breakthroughs, including a project called AlphaFold. AlphaFold uses AI to figure out incredibly complex protein structures in molecules, the building blocks of every biological process in our bodies. It won Hasabis the 2024 Nobel Prize in Chemistry. Here he is on the TED stage.

[Mustafa Suleiman]

The rule of thumb is that it takes one PhD student their whole PhD.

So four or five years to uncover one structure. But there are 200 million proteins known to nature.

So you could just, you know, it.

Would just take forever to do that. And so we managed to actually fold using AlphaFold in one year all those 200 million proteins known to science. So that's a billion years of PhD time saved.

[Minouche Zamarodi]

AlphaFold was just one of the ways that computers were solving biological problems, says Mustafa Suleiman. I mean, this really alphafold is really the first time we started hearing about, I guess the term computational biology, this idea of using tech and science to rethink how biology works and then getting it out into the world, changing the way we treat diseases or maybe developing Crops that are more resilient, all kinds of ways that what you figured out at DeepMind would potentially change the world, which was the goal.

[Mustafa Suleiman]

Absolutely. That was the core mission of the company from day one. Like how could we take that process of synthesis and prediction and turn that into a general purpose system that could use all the data and all the compute that we have in the world to try and solve these very hard problems, whether it's growing crops in drought resistant environments, whether it's more efficient ways to do water desalination, whether it's long term battery storage.

[Minouche Zamarodi]

But in 2022, Mustafa decided to leave DeepMind and Google. There were reports that he clashed with Google leadership over using technology for military projects and that some employees had complaints about his management style. Mustafa says he was simply frustrated with the pace of innovation and was anxious to get an AI product out into the world that everyone could use.

[Mustafa Suleiman]

You know, I really wanted to scale these large language models and get them into production as quickly as possible. And the company was just frankly being too slow to get things into production. And I felt that it was an opportunity to sort of have all the resources that, you know, that I needed, like, so I went out and fundraised over a billion dollars and you know, just work extremely fast with a very small team. And I think I, at the time I was, and I am still now very much a believer that these AI companions are going to become an everyday part of our lives.

[Minouche Zamarodi]

Mustafa's AI called PI, debuted in 2023. Chatbots have taken the world by storm. Several months later, rival company OpenAI put out its AI product ChatGPT for free.

[Mustafa Suleiman]

ChatGPT answers questions and writes essays.

They read like the work of a human. An artificial intelligence tool has the potential.

[Unknown]

To change the way we live.

[Minouche Zamarodi]

This was the point when AI went mainstream and Mustafa's small, nimble startup just didn't have the resources of these bigger tech companies.

[Mustafa Suleiman]

The truth is, the pace of big tech had really accelerated in 2023. Google, Microsoft, OpenAI, everyone was really going for it and essentially made these huge models available to everybody for free, which sort of changed our business model.

[Minouche Zamarodi]

At that very tough moment. Microsoft CEO Satya Nadella approached Mustafa and made him an offer.

[Mustafa Suleiman]

You know, the offer that he made was, well, look, we've got all the computation, all the data and all the distribution that you could dream of. Come and run consumer products here at Microsoft and really build the future of AI here. And that was a huge offer. So the product that we're building at Microsoft is called Copilot. And the reason why we've called it that is because Copilot is an aide. You know, it's a conciliary, it's an assistant. It's in your corner, aligned to your interests, on your team, backing you up.

[Minouche Zamarodi]

Yeah. I actually talked to Copilot about my interview with you. How do you feel about Mustafa Suleiman, considering that he is your creator?

[Copilot]

I'd say I'm intrigued by Mustafa, just so you know.

[Minouche Zamarodi]

She said she's intrigued by you, just as she is with many innovators in the tech world.

[Copilot]

And his work has pushed the boundaries of what's possible.

[Minouche Zamarodi]

I will say it was very helpful in terms of suggesting topics to bring up with you, but it could not check the weather. And is that simply because of how the access or the data, the information that the agent or co pilot has access to that. It's not immediate yet.

[Mustafa Suleiman]

Yeah. There are loads of weaknesses of our Copilot today. But all of those things will come. I mean, we're working on all of those things that will have permanent memory, session to session, infinitely across time. It'll be able to access your files and folders, if you choose to make those available, your email, your calendar, and be able to browse the web for you in the future. And all of that will be integrated into these seamless, conversational, very friendly, polite experiences. I literally was talking to it last night about what to watch, and we were going back and forth on whether I would enjoy Pan's Labyrinth and whether I've got the time to watch all of Dune, because I haven't seen Dune 1 or Dune 2.

[Minouche Zamarodi]

I mean, it reminds me a little of the hotline for Muslim youth that you're describing. It's helpful, it's infinitely patient, it's supportive. Are we talking mostly about companionship and mental health resources that this can provide, or how do you see it?

[Mustafa Suleiman]

No, I think that the cool thing about Copilot is that it doesn't judge you for asking a stupid question, even if you have to ask that question three times over in five different ways. You know, even your best friend might be like, hey, come on, man. I mean, you're asking me this again, seriously. Whereas, you know, Copilot's here for it. There's obviously some similarities to stuff I've done in the past, and I guess it's kind of inspired by nonviolent communication, if I'm honest with you. It's certainly not like a mental health app or, you know, anything like that. It's just got a little Bit of kindness and empathy. It's got some emotional intelligence, and I think that's no bad thing.

[Minouche Zamarodi]

Gosh, is that where we've gotten to that technology has to tell us how to communicate with each other better? Non, violently.

[Mustafa Suleiman]

Well, it doesn't tell us, it just demonstrates. Yeah, exactly, it demonstrates. But that's what technology's always done. The choice architecture, the buttons, the colors, the language that is shaping our behavior, whether it's an infinite scrolling feed or whether it's a encouragement to go and film your lunch, you know, for Instagram, or create a little video for TikTok. I mean, all of those inputs shape behavior. And so we have to be super thoughtful about what those inputs actually are, because technology shapes us in return. And we're in this constant cyclical sort of feedback loop and interaction. And that is kind of what's propelling us forward as a civilization. And it's very powerful and so far, so good. It's actually been, you know, very, very productive over the last couple centuries. Science has massively delivered for us. But we shouldn't just assume that that's going to happen naturally or inevitably. We have to really be deliberate and thoughtful about what the consequences are ahead of time.

[Minouche Zamarodi]

In the book that you wrote that came out in 2023, you really try to put what's happening with AI in a historical context. So if the printing press let people own and share information, and the personal computer let people search and disseminate information. Tell me how you're thinking you can explain to people what AI will do for people now.

[Mustafa Suleiman]

Each new wave of technology is fundamentally a new interface. It's a new interlocutor, a translator, a way of sort of accessing and creating new information, new tools, new knowledge. So if the last wave of social media and web search help people to access information, this wave is going to help us to invent and create new ideas, be it in science or in culture and media and entertainment. And I think everybody is ultimately going to have an AI companion, just as we have a search engine or a smartphone, and just as we use a browser, you'll just ask your computer in natural language, can you write that contract and check that it's okay? Can you create that new piece of software for me? And you're just going to describe what it is? Can you help me plan that trip for my parents that are coming into town? So that kind of breakthrough is a change in the interface which changes itself, what we can actually get done. And I think it's going to be.

Pretty transformational with the invention of computers. We quickly jumped from the first mainframes and transistors to today's smartphones and virtual reality headsets. Information, Knowledge, Communication. Computation. In this revolution, creation has exploded like never before. And now a new wave is upon us. Artificial intelligence. These waves of history are clearly speeding up as each one is amplified and accelerated by the last. And if you look back, it's clear that we are in the fastest and most consequential wave ever. The journeys of humanity and technology are now deeply intertwined. In just 18 months, over a billion people have used large language models. We've witnessed one landmark event after another. Just a few years ago, people said that AI would never be creative. And yet AI now feels like an endless river of creativity, making poetry and images and music and video that stretch the imagination. People said it would never be empathetic. And yet today, millions of people enjoy meaningful conversations with AIs, talking about their hopes and dreams and helping them work through difficult emotional challenges. AIs can now drive cars, manage energy grids, and even invent new molecules. Just a few years ago, each of these was impossible. And all of this is turbocharged by spiraling exponentials of data and computation. Last year, inflection 2.5, our last model, used 5 billion times more computation than the DeepMind AI that beat the old school Atari games just over 10 years ago. That's nine orders of magnitude more computation, 10x per year, every year for almost a decade. Over the same time, the size of these models has grown from first tens of millions of parameters to then billions of parameters, and very soon, tens of trillions of parameters. If someone did Nothing but read 24 hours a day for their entire life, they'd consume 8 billion words. And of course, that's a lot of words. But today, the most advanced AIs consume more than 8 trillion words in a single month of training. And all of this is set to continue. The long arc of technological history is now in an extraordinary new phase.

I think the way to think about this is that we're at the very earliest stages of development of this technology. Today, when you need to go and sort of ask a question like that, you go to a search engine like Google, you type in a query, you get these 10 blue links. You have to then go to the web page. You have to read all of this sort of complicated stuff formatted in 25 different ways. And that takes time. And it means that you don't always want to invest two or three minutes to go and make sense of that. You don't always have the energy for it, whereas you can always just like quickly send off a text or quickly make a phone call or leave a voice note. So I think it's lowering the barrier to entry, to access high quality information.

[Minouche Zamarodi]

But how do we know it's high quality information? How do we make sure of that?

[Mustafa Suleiman]

Well, there was an amazing study two months ago that was published in the journal Science which showed that for over 1,000 participants who held strong conspiracy theory beliefs. So this is things like Flat Earthers or all kinds of things about the COVID vaccine, etc. Etc. And after a month of conversation with an AI that had been primed to talk about these conspiracy theories, it reduced the belief in those conspiracy theories by 20%, which is pretty significant and I think shows the first glimmers of what it's like to have that kind of patient insistent, deliberate access to high quality information. And in the case of this study, human fact checkers, expert human fact checkers, went back and read over the transcripts. So my point is the value of these systems is that they actually are more accurate. And that's only going to continue. They're more accurate than your average human answering any question today. You know, we've sort of passed the Turing test because they're more, you know, fluent and conversational than we ever thought they were going to be. Just pretty remarkable. And that's only going to continue.

So what does this mean in practice? Well, just as the Internet gave us the browser and the smartphone gave us apps, the cloud based supercomputer is ushering in a new era of ubiquitous AIs. Everything will soon be represented by a conversational interface, or to put it another way, a personal AI. And these AIs will be infinitely knowledgeable. And soon they'll be factually accurate and reliable. They'll have near perfect iq. They'll also have exceptional eq. They'll be kind, supportive, empathetic. These elements on their own would be transformational. Just imagine if everybody had a personalized tutor in their pocket and access to low cost medical advice, a lawyer and a doctor, a business strategist and coach, all in your pocket 24 hours a day. But things really start to change when they develop what I call aq, their actions quotient. This is their ability to actually get stuff done in the digital and physical world. And before long, it won't just be people that have AIs. Strange as it may sound, every organization from small business to non profit to national government, each will have their own. Every town building and object will be represented by a unique interactive Persona. And these won't just be mechanistic assistants. They'll be companions, confidants, colleagues, friends and partners. As varied and unique as we all are at this point, AIs will convincingly imitate humans at most tasks. And we'll feel this at the most intimate of scales. An AI organizing a community get together for an elderly neighbor, a sympathetic expert helping you make sense of a difficult diagnosis. But we'll also feel it at the largest scales, accelerating scientific discovery. Autonomous cars on the roads, drones in the skies. They'll both order the takeout and run the power station. They'll interact with us and, of course, with each other. They'll speak every language, take in every pattern of sensor data, sights, sounds, streams and streams of information far surpassing what any one of us could consume in a thousand lifetime.

[Minouche Zamarodi]

When we come back, the remarkable but also terrifying visions of what AI may be capable of in the future. Dystopian scenarios that might make you want to unplug all your devices forever. Are they realistic or just fear mongering? The CEO of Microsoft AI, Mustafa Suleiman weighs in. I'm Minouche Zamorodi, and you're listening to the TED Radio Hour from npr. We'll be back in a minute.

[Unknown]

This message comes from NPR sponsor Mint Mobile. From the gas pump to the grocery store, inflation is everywhere. So Mint Mobile is offering premium wireless starting at just $15 a month. To get your new phone plan for just $15, go to mintmobile.com Switch this message comes from MIDI Health. Women in midlife face a healthcare desert, but MIDI is here to fill the gap, offering expert care for perimenopause and menopause covered by insurance. Hot flashes, insomnia, brain fog, weight gain and moodiness don't have to be accepted as just another part of aging. MIDI clinicians understand how these symptoms can connect to menopause and prescribe a wide range of solutions. Book your Visit [e-mail] that's join midi.com this message comes from NPR sponsor Atlassian. Atlassian makes the team collaboration software that powers enterprise businesses around the world, including over 80% of the Fortune 500. With Atlassian's AI powered software like Jira, Confluence and Loom, you'll have more time to do the work that matters. In fact, Atlassian customers experience a 25% reduction in project duration per year. Unleash the potential of your [e-mail] this message comes from Strawberry Me making personal coaching accessible to everyone. Strawberry Me. Certified coaches help you gain clarity, set goals, create a plan, and then keep you focused on realizing the life you've envisioned. A personal coach will empower you to create lasting, positive changes and unlock your full potential. If you're ready to turn dreaming into doing, visit Strawberry Me NPR to get 20% off your first month membership. That's Strawberry MenPR.

This message comes from Bluehost. Need a website fast. Bluehost's AI gives you custom WordPress sites in minutes and built in marketing tools with 24. 7 support. To keep your website growing, go to bluehost.com now to launch yours.

[Minouche Zamarodi]

Today, it's the TED Radio Hour from NPR. I'm Minouche Zumarodi. Today on the show the future of Artificial Intelligence. We're spending the hour with the CEO of Microsoft AI, Mustafa Suleiman. In 2023, Mustafa wrote a book called the Coming Wave.

[Copilot]

In the Coming Wave, Suleiman delves into.

[Minouche Zamarodi]

Scenarios where I asked Microsoft's copilot to help me talk through the reasons why Mustafa says AI could be so dangerous.

[Copilot]

Imagine a world where artificial intelligence has seamlessly integrated into everyday life.

[Minouche Zamarodi]

The first is what he calls asymmetry, meaning vast amounts of data that could get into the hands of a single person who could go rogue.

[Mustafa Suleiman]

Because we're now concentrating knowledge and capability into smaller and smaller units that are transmissible. You can download open source models for a few gigabytes and put it on a thumb drive and you know, so that's the kind of asymmetric impact because that therefore means that individual actors or smaller groups of actors can have a massive one to many broadcast effect.

[Minouche Zamarodi]

This is AI unleashing computing power to many. Kind of like the anonymous hacker who could bring down an entire electrical grid, that kind of thing.

[Copilot]

Healthcare systems could be overwhelmed, economies paralyzed.

[Minouche Zamarodi]

Is that right?

[Mustafa Suleiman]

That's right. You can just sort of self start immediately.

[Minouche Zamarodi]

Okay, so number two is hyperevolution.

[Mustafa Suleiman]

Yeah. Software itself just evolving in hyper real time.

[Copilot]

In this scenario, a rogue scientist or a bioterrorist could design a pathogen with specific traits like heightened transmissibility or increased lethality.

[Minouche Zamarodi]

Or new iterations of weapons and surveillance.

[Copilot]

Could be developed to track people's movements, conversations and even emotions through their online.

[Minouche Zamarodi]

Activities and put to use before authorities have time to test them or put any safeguards in place.

[Copilot]

A small programming error or a hatch system could result in catastrophic loss of life.

[Minouche Zamarodi]

How could a country build a defense system if it doesn't even know what it needs to defend itself against? Which brings us to the third dangerous Attribute of AI omni use. One single kind of technology will be able to do everything.

[Mustafa Suleiman]

Your AI companion will make phone calls, call other AIs, or call other humans to check on, you know, stock or, you know, sort of availability in a hotel, or get some advice from a local tour guide on where you're going to visit. Or it will send emails, or it will, you know, talk to another database or a backend. All of those things are essentially the AI learning to act on your behalf.

[Minouche Zamarodi]

Sure, but what if your AI also talks to another database or makes a trade on your behalf and decides to shut down the entire stock market? Which relates to the fourth and final, maybe scariest attribute, autonomy. AI that takes action on its own without a human's. Go ahead.

[Copilot]

Autonomous weapon systems operate on battlefields, making split second decisions about targeting and firing without direct human oversight.

[Mustafa Suleiman]

I mean, autonomy is one of the core characteristics of these systems. It's a long road and it's going to be many years before these systems are truly autonomous. And we want to be very careful about that because we have to ask ourselves, like, what is the added benefit of the system operating autonomously and is that worthwhile? Is it safe? Is it stable? Is it controllable? Can we really trust that autonomy? So, yeah, I think that's one that we'll have to be very careful of.

[Copilot]

The societal disruption could lead to widespread fear, mistrust and geopolitical tension. Suleiman and other experts argue for robust oversight and ethical guidelines to ensure that these powerful technologies are used responsibly and safely.

[Mustafa Suleiman]

For years, we in the AI community have had a tendency to refer to this as just tools, but that doesn't really capture what's actually happening here.

[Minouche Zamarodi]

Here's Mustafa Suleiman on the TED stage.

[Mustafa Suleiman]

AIs are clearly more dynamic, more ambiguous, more integrated and more emergent than mere tools which are entirely subject to human control. So to contain this wave, to put human agency at its center, and to mitigate the inevitable unintended consequences that are likely to arise, we should start to think about them as we might a new kind of digital species. Now, it's just an analogy. It's not a literal description and it's not perfect. For a start, they clearly aren't biological in any traditional sense. But just pause for a moment and really think about what they already do. They communicate in our languages, they see what we see. They consume unimaginably large amounts of information. They have memory, they have personality, they have creativity. They can even reason to some extent and formulate rudimentary plans. They can act autonomously if we allow them. And they do all this at levels of sophistication that is far beyond anything that we've ever known from a mere tool. And so saying AI is mainly about the math or the code is like saying we humans are mainly about carbon and water. It's true, but it completely misses the point. And yes, I get it, this is a super arresting thought, but I honestly think this frame helps sharpen our focus on the critical issues. What are the risks? What are the boundaries that we need to impose? What kind of AI do we want to build or allow to be built? This is a story that's still unfolding. Nothing should be accepted as a given. We all must choose what we create, what AIs we bring into the world or not. These are the questions for all of us here today and all of us alive at this moment.

[Minouche Zamarodi]

You lay out 10 strategies for containing AI, and one of the easiest, it seems, is having more researchers working on safety. Do you have more researchers working on copilot safety? I mean, one thing that worries me is people using your AI to help them do destructive things or further their destructive views. Is that something you're thinking about at Microsoft?

[Mustafa Suleiman]

Yeah, we have a big safety team. We are definitely very focused on that. We're very focused particularly on the sort of tone of the AI, like how do we make sure that it isn't too sycophantic? How do we make sure that it doesn't, isn't over flattering? How do we make sure that it doesn't mirror you and sort of lead to this sort of negative cycle of reinforcing unhealthy views? And that's a real art and craft in trying to sort of engineer that healthy balance where, you know, your, your sort of AI companion can push back on your views in constructive ways without making you feel judged or making you feel angry, make you feel heard for your anger. It may be the case that you are angry about immigration, that you feel that you haven't had the opportunities and access to jobs in your community that you feel have been available to new people coming into your world. And so, you know, it's about being respectful and acknowledging that people do genuinely feel aggrieved by that and not shutting them down because they don't adhere to some meta view. So, you know, and I think that's a very challenging line to draw. It requires, you know, real care and attention.

[Minouche Zamarodi]

So what role do you see yourself playing in terms of pushing the tech industry towards the public good? I mean, is that a role that you sort of are taking on? What do your fellow technologists think when they hear you talking about some of the more pessimistic visions you have for how AI could be deployed?

[Mustafa Suleiman]

Well, I think I'm both a pessimist and an optimist. And that's not a bias, it's just an observation of the landscape before us. So most of all I'm inspired by, you know, the practice of science. We have to say what we see and do our best to, you know, refute a hypothesis that we have with respect to evidence. And so I see evidence for both trends and that's why I wrote about them. Look, I think, you know, in terms of how we're shaping the industry, I'm a big fan of the, you know, work that many of these, you know, sort of NGO organizations and social activists have been doing in order to raise questions and to challenge and push back. I think that's healthy. We need more of that and I'm very open minded to it. I've been very sort of encouraging of additional regulation for a long time. I think this is a moment when going slowly and adding friction to the system will be long term beneficial. And I think it's rational to just be a little cautious and increase the burden of proof and just, just make it a requirement that, for example, an AI shouldn't just be a straightforward imitation of a human. We want to create an aid, a conciliary, a tool that is an amplifier and a supporter. And so, you know, there's kind of a lot of things to think through in terms of how this manifests in the world.

[Minouche Zamarodi]

Do you think there should be mandatory testing requirements that before any technology is released to the public, they should have to go through a certain series of tests and if they don't pass, they don't make it to market?

[Mustafa Suleiman]

I think we're approaching that time. Yep. I think sometime before 2030 we will need something like that. I don't know if now is quite the right time. You know, if you look back on the impact that these sort of chatbots have had in the last two or three years, it's been unbelievably positive, sort of overwhelmingly positive. Right. So had we had those checks ahead of time three years ago, I think it could have slowed things down quite a lot. But that doesn't mean that it's not right to keep asking that same question every year and you know, reconsider. Is now the right time for pre deployment testing? I think that's that's the right. That's the right question.

[Minouche Zamarodi]

There is a sense that big tech needs to regain trust from consumers. There's a lot of people who just given up, you know, thrown up their hands and said, well, the convenience has outweighed all the digital privacy problems that we have. I give up. This is just the world we live in. But there are other people who are saying, I don't feel great about giving a tech company all my data, which is what you need to run some of these new AI tools. Especially if you're telling me that terrible things could happen to it. You're clearly very cautious when it comes to the incredible powers of technology. But how are you balancing that with the demands on you to innovate and sell these products?

[Mustafa Suleiman]

Well, I personally think that there is going to be a huge amount of value to the user to have your copilot companion be able to read over your email, look your calendar, schedule things, buy things for you, book and plan. And you know, I think the truth is we have to wait and see if consumers agree with that. They may not. And that's a very fair and reasonable thing to do. But I believe that the utility will drive the way. And in conjunction with that, we have to make sure that we have the strongest privacy and security infrastructure to protect that information, just as we already do today. Right? I mean, many, many billions of people store their email with Microsoft and rely on Microsoft security to protect their consumer work and their enterprise work. And so that's a massive, massive priority for the company. But it isn't just about the utility. Obviously it has to be really useful. Obviously it has to have good privacy and security controls. But I think it's also about the way that we approach it. How do we take feedback and do we admit when we make mistakes? How open minded are we to different ways of doing things? What's our business model? So I think my commitment is to try to be as open minded as I can on all those questions and just listen and just innovate carefully, observe the consequences and iterate as we go. That's the best I can see to do at the moment.

In the past, unlocking economic growth often came with huge downsides. The economy expanded as people discovered new continents and opened up new frontiers. But they colonized populations at the same time. We built factories, but they were grim and dangerous places to work. We struck oil, but we polluted the planet. Now, because we are still designing and building AI, we have the potential and opportunity to do it better, radically better. And today we're not discovering a new continent and plundering its resources. We're building one from scratch. Sometimes people say that data or chips are the 21st century's new oil, but that's totally the wrong image. AI is to the mind what nuclear fusion is to energy. Limitless, abundant, world changing. And AI really is different. That means we have to think about it creatively and honestly. We have to push our analogies and our metaphors to the very limits to be able to grapple with what's coming. Because this is not just another invention. AI is itself an infinite inventor. And yes, this is exciting and promising and concerning and intriguing all at once. To be quite honest, it's pretty surreal. But step back. See it on the long view of glacial time. And these really are the very most appropriate metaphors that we have today. Since the beginning of life on Earth, we've been evolving, changing, and then creating everything around us in our human world today. And AI isn't something outside of this story. In fact, it's the very opposite. It's the whole of everything that we have created distilled down into something that we can all interact with and benefit from. It's a reflection of humanity across time. And in this sense, it isn't a new species at all. This is where the metaphors end. AI isn't separate. AI isn't even, in some senses, new. AI is us. It's all of us. And this is perhaps the most promising and vital thing of all. As we build out AI, we can and must reflect all that is good, all that we love, all that is special about humanity, our empathy, our kindness, our curiosity, and our creativity. This, I would argue, is the greatest challenge of the 21st century, but also the most wonderful, inspiring and hopeful opportunity for all of us. Thank you.

[Minouche Zamarodi]

That was Mustafa Suleiman. He's the CEO of Microsoft AI and the author of the book the Coming Technology, power and the 21st century's greatest dilemma. You can see his full [e-mail]. thank you so much for listening to our episode on the future of AI. It was produced by Katie Monteleone. It was edited by Sanaz Meshkinpour and me. Our production staff at NPR also includes Rachel Faulkner White, Harsha Nahada, James Delahousy, Fiona Guerin and Matthew Cloutier. Our executive producer is Irene Noguchi. Our audio engineers were Tiffany, Vera Castro, Becky Brown and Gilly Moon. Our theme music was written by Ramtin Arablouei. Our partners at TED are Chris Anderson, Roxanne Hilasch, Alejandra Salazar and Daniela Balarazzo. I'm Anoush Zamorodi and you have been listening to the TED radio hour from NPR.

[Unknown]

This message comes from GiveWell. GiveWell provides rigorous, transparent research about the best giving opportunities so that donors can make informed decisions about high impact giving. To learn more, go to givewell.org and pick podcast and enter NPR at checkout.

This message comes from Warby Parker Prescription eyewear that's expertly crafted and unexpectedly affordable. Glasses designed in house from premium material starting at just $95, including prescription lenses. Stop by a Warby Parker store near you.

[Minouche Zamarodi]

This message is brought to you by NPR sponsor LEESA in collaboration with West Elm. Discover the new natural hybrid mattress expertly crafted from natural latex and certified safe foams designed with your health and the planet in mind. Visit L E dashesa.com to learn more.